Robbie Allen @ Tweener Claw: "3 to 5 of My Agents Fail Every Day: Here's What I've Learned"
In this episode of Tweener Claw, Robbie Allen, the Founder and Managing Director of Automated Consulting Group and General Partner at NC Tweener Fund, shares a live talk from the June 10th Tweener Club meetup in Research Triangle Park.
Robbie has spent the last year and a half deploying AI agents inside real mid-market companies, and he brings three lessons from just the last 60 days: how to build reusable AI skills that compound over time, how to monitor agents when 3 to 5 of your 25-plus will fail on any given day, and why using multiple LLMs to check each other's work has become a standard part of his workflow. Each lesson comes with a real-world example: a three-skill meeting pipeline, a monitor agent that watches the others, and a Codex Opinion skill that consistently finds gaps in Claude's output.
The sharpest takeaway: AI build costs have dropped dramatically, but support and maintenance costs have not. Non-deterministic systems are inherently brittle, and anyone telling you otherwise hasn't run them in production long enough. This is a practitioner's talk for practitioners; specific, candid, and immediately actionable.
Timestamps
01:31 Scot's intro
02:03 60 days of lessons
02:19 Three lessons preview
03:08 Robbie takes the stage
03:25 About Automated Consulting Group
04:13 Reality vs. the AI hype cycle
05:04 The Microsoft / Copilot rant
07:13 Lesson 1: Skills that build skills
08:41 Skills as reusable packages
09:21 "The sawdust of business"
10:58 Building a skills pipeline for meetings
11:57 Skills security risks in the enterprise
12:47 Lesson 2: Agents watching agents
13:44 Build costs are down
14:24 "3 to 5 of my agents fail every day"
15:44 Log everything
17:33 What causes agents to fail in the wild
18:02 Lesson 3: LLMs checking LLMs
18:13 The LLM Council concept explained
19:44 The case for a multi-LLM strategy
20:36 The "Codex Opinion" skill 21:33 Gemini Opinion & LLM Council in action
23:46 Wrap-up & credits
---
This episode of Triangle Tweener Talks is hosted by Scot Wingo, and presented and produced by NC Tweener Fund, with creative assets and design support from Walk West.
We couldn’t share posts like this without our amazing sponsors:
Platinum:
NC IDEA: https://ncidea.org
Gold Sponsors:
- Balentine: https://www.balentine.com/triangle-entrepreneurs
- EisnerAmpner: https://www.eisneramper.com
- Robinson Bradshaw: https://www.robinsonbradshaw.com
Silver Sponsors:
- Automated Consulting Group: https://automated.co
- Bank of America: https://business.bofa.com/en-us/content/technology-industry-group.html
Robbie has spent the last year and a half deploying AI agents inside real mid-market companies, and he brings three lessons from just the last 60 days: how to build reusable AI skills that compound over time, how to monitor agents when 3 to 5 of your 25-plus will fail on any given day, and why using multiple LLMs to check each other's work has become a standard part of his workflow. Each lesson comes with a real-world example: a three-skill meeting pipeline, a monitor agent that watches the others, and a Codex Opinion skill that consistently finds gaps in Claude's output.
The sharpest takeaway: AI build costs have dropped dramatically, but support and maintenance costs have not. Non-deterministic systems are inherently brittle, and anyone telling you otherwise hasn't run them in production long enough. This is a practitioner's talk for practitioners; specific, candid, and immediately actionable.
Timestamps
01:31 Scot's intro
02:03 60 days of lessons
02:19 Three lessons preview
03:08 Robbie takes the stage
03:25 About Automated Consulting Group
04:13 Reality vs. the AI hype cycle
05:04 The Microsoft / Copilot rant
07:13 Lesson 1: Skills that build skills
08:41 Skills as reusable packages
09:21 "The sawdust of business"
10:58 Building a skills pipeline for meetings
11:57 Skills security risks in the enterprise
12:47 Lesson 2: Agents watching agents
13:44 Build costs are down
14:24 "3 to 5 of my agents fail every day"
15:44 Log everything
17:33 What causes agents to fail in the wild
18:02 Lesson 3: LLMs checking LLMs
18:13 The LLM Council concept explained
19:44 The case for a multi-LLM strategy
20:36 The "Codex Opinion" skill 21:33 Gemini Opinion & LLM Council in action
23:46 Wrap-up & credits
---
This episode of Triangle Tweener Talks is hosted by Scot Wingo, and presented and produced by NC Tweener Fund, with creative assets and design support from Walk West.
We couldn’t share posts like this without our amazing sponsors:
Platinum:
NC IDEA: https://ncidea.org
Gold Sponsors:
- Balentine: https://www.balentine.com/triangle-entrepreneurs
- EisnerAmpner: https://www.eisneramper.com
- Robinson Bradshaw: https://www.robinsonbradshaw.com
Silver Sponsors:
- Automated Consulting Group: https://automated.co
- Bank of America: https://business.bofa.com/en-us/content/technology-industry-group.html
------
Triangle Tweener Talks is sponsored by:
Triangle Tweener Talks is sponsored by:
- Atomic Object: https://atomicobject.com/
